Penerapan Convolutional Neural Network dan Evaluation Based on Distance from Average Solution dalam Sistem Cerdas Kesesuaian Frame Kacamata dengan Identifikasi Bentuk Wajah

Abstract

Glasses are vision aids that consist of a pair of lenses mounted in a frame. Typically, glasses are used by individuals with vision problems such as myopia, hypermetropia, or astigmatism to help focus incoming light for clearer vision. Nowadays, the use of glasses has undergone a transformation. Glasses are no longer just for improving vision clarity but have become an important part of lifestyle and fashion. They are often used as accessories to enhance a person's appearance, making them look more attractive. When choosing glasses frames it is important to consider several aspects one of which is adjusting to the shape of the face. Because the frame is very visible on the face, its shape can emphasize or reduce facial features. Therefore, an intelligent system is needed to help determine the appropriate glasses frame by identifying the shape of the face using the Convolutional Neural Network algorithm and a Decision Support System with the Evaluation based on Distance from Average Solution (EDAS) method to produce the most suitable eyeglass frame recommendations. This study conducted software testing using the black box testing method, employing photos of individuals both adhering to and deviating from the established criteria. Additionally, various criteria were tested to generate eyeglass frame recommendations. The results of this study indicate that the facial shapes of individuals who meet the requirements can be accurately and consistently identified, and the recommendations provided align with the criteria needed by users.